Nick Heiner

You know, I'll give you another example of this, which is many coding agents do not want to use external libraries unless you really force them to do so.

When you say I have a bunch of like, you know, chess puzzles and I want you to write a program is going to solve them.

The obvious thing to do is to get Stockfish, just write a little wrapper, and then spit that out.

If you're saying this is for a production system, I'm building a chess app, yeah, just get Stockfish.

Models want to make their own chess solver.

Yeah, they want to build it from scratch.

Because that's what you would do in an academic setting.

You're not being tested on your ability to use Stockfish.

You know, it's like those memes, you know, guys will do anything to avoid going to therapy.

It's like, you know, similarly, it's like coding models will do anything to avoid using the already perfectly good available library.

And I do think it's a great feature of these models that we will be perhaps reaching for left pad less frequently because you can just have the confidence that your model can write that 10 line function for you.

Yeah.

But there's a tie back to finance.

Like, yeah, what we see is like excellence on sort of the core thing you would do in school versus

But then when there are a lot of details or especially when the task is structured, not as I've given you everything in the prompt, all neatly bundled up.

But you need to go into our environment and like search through our confluence to find like our standard procedure for how we model this scenario.

Check your email from a note for the VP that said, you know, here's some other important context for how this analysis needs to be done.

You know, we got five different CSVs from the client.

One of them is the relevant one.

The other four are out of date now.